Parijat Deshpande

Smartphone Based Digital Stethoscope for Connected Health -- A Direct Acoustic Coupling Technique

Mobile smartphones have revolutionized the concept of mobile phones as different apps are built to offer various interesting applications in healthcare, gaming, etc. rather than using the phone only for voice services. The application developers take advantage of onboard sensors, web connectivity and powerful processing units of the smartphones to develop such interesting apps. In this paper, we present an interesting approach where direct acoustic coupling technique is employed to quickly and conveniently convert the smartphones into high quality digital stethoscope by using an ultra-low cost attachment. The design consideration primarily focused on affordability, simplicity and use-friendly aspects into account. The motivation of this work is to enable the heart patients to send their heart sound to doctors chamber/ hospitals from their home instead of travelling all the way to hospitals/clinics. This is particularly useful in poor or developing countries where there is scarcity of healthcare centers and patients have to travel a long distance to visit the clinic. The situation becomes more serious in case of patients who went through heart surgery and requires follow up visits or for elderly population requiring routine checkups. For both the cases, in many instances, doctors primarily listen to the heart sound to prescribe further actions. Our solution can greatly help such situations and in many cases it can completely eliminate the travel. In addition, since data can also be recorded and saved, this opens up possibility for statistical analysis to further aid the diagnosis / monitoring. Thus, our solution can serve as a viable tool in connected health use cases for heart patients for needy geography.

A next generation mobile robot with multi-mode sense of 3D perception

Robotic platforms are becoming increasingly important and have their utility and cost completely justified during missions which require substituting humans. In this paper, we present our ongoing work in developing a multi-sensor robotic platform intended for deploying in an indoor environment in hazardous situations. The prime objective of such portable robots will be to conduct surveillance missions and provide a perception of its surroundings to the human-in-loop to ascertain the uncertain environment. Therefore, the robotic platform needs to be equipped with various sensors to create 3D visual maps of its surroundings. However, given the compact size and hazardous nature of the missions expensive LIDAR equipment may not be always suitable. We propose developing an integrated platform comprising of low cost optical cameras, acoustic localization via microphones and low cost alternatives are explored albeit with limited functionality and ultrasonic acoustic imaging arrays and augmenting these 3D maps with thermal imagery data. The aim of such a system will be to perform well even in dark and smoky environments via active ultrasonic imaging. A decision support system will equip the robot with the ability to prioritize appropriate sensors depending on the scenario. The choice of various proprioceptive and exteroceptive sensors are based on their significantly lower price tag as compared to the systems available in the market. This robotic platform will serve as a test-bed for performing various complex tasks such as discovering occluded objects, improved perception in dark and smoky environments as well as thermal source detection.

Emotion detection and recognition using HRV features derived from photoplethysmogram signals

Detection of true human emotions has attracted a lot of interest in the recent years. The applications range from e-retail to health-care for developing effective companion systems with reliable emotion recognition. This paper proposes heart rate variability (HRV) features extracted from photoplethysmogram (PPG) signal obtained from a cost-effective PPG device such as Pulse Oximeter for detecting and recognizing the emotions on the basis of the physiological signals. The HRV features obtained from both time and frequency domain are used as features for classification of emotions. These features are extracted from the entire PPG signal obtained during emotion elicitation and baseline neutral phase. For analyzing emotion recognition, using the proposed HRV features, standard video stimuli are used. We have considered three emotions namely, happy, sad and neutral or null emotions. Support vector machines are used for developing the models and features are explored to achieve average emotion recognition of 83.8% for the above model and listed features.

PerDMCS: Weighted Fusion of PPG Signal Features for Robust and Efficient Diabetes Mellitus Classification.

Non-invasive detection of Diabetes Mellitus (DM) has attracted a lot of interest in the recent years in pervasive health care. In this paper, we explore features related to heart rate variability (HRV) and signal pattern of the waveform from photoplethysmogram (PPG) signal for classifying DM (Type 2). HRV features includes timedomain (F1), frequency domain ( F2), non-linear features ( F3) where as waveform features ( F4) are one set of features such as height, width, slope and durations of pulse. The study was carried out on 50 healthy subjects and 50 DM patients. Support Vector Machines (SVM) are used to capture the discriminative information between the above mentioned healthy and DM categories, from the proposed features. The SVM models are developed separately using different sets of features F1, F2, F3,andF4, respectively. The classification performance of the developed SVM models using time-domain, frequency domain, non-linear and waveform features is observed to be 73%, 78%, 80% and 77%. The performance of the system using combination of all features is 82%. In this work, the performance of the DM classification system by combining the above mentioned feature sets with different percentage of discriminate features from each set is also examined. Furthermore weight based fusion is performed using confidence values obtained from each model to find the optimal set of features from each set with optimal weights for each set. The best performance accuracy of 89% is obtained by scores fusion where combinations of mixture of 90% features from the feature sets F1 and F2 and mixture of 100% features from the feature sets F3 andF4, with fusion optimal weights of 0.3 and 0.7, respectively.

Noise detection in smartphone phonocardiogram

This paper presents a demo proposal of a standalone smartphone application that can automatically analyse the signal quality of PCG, as it is recorded on a low-cost smartphonebased digital stethoscope. Features, related to the inherent pattern of the autocorrelated signal envelope, have been used for classifying and discarding the noisy portions from a continuous PCG. Our application has been successfully deployed on Nexus 5 and tested on several clean and noisy PCG signals with sensitivity 78.91% and specificity 70.83%